vserver 1.9.5.x5

[linux-2.6.git] / arch / ppc64 / oprofile / op_model_power4.c

diff --git a/arch/ppc64/oprofile/op_model_power4.c b/arch/ppc64/oprofile/op_model_power4.c
index b2a512c..b1ca798 100644 (file)
--- a/arch/ppc64/oprofile/op_model_power4.c
+++ b/arch/ppc64/oprofile/op_model_power4.c
@@ -32,6 +32,13 @@ static u32 mmcr0_val;
 static u64 mmcr1_val;
 static u32 mmcra_val;
 
+/*
+ * Since we do not have an NMI, backtracing through spinlocks is
+ * only a best guess. In light of this, allow it to be disabled at
+ * runtime.
+ */
+static int backtrace_spinlocks;
+
 static void power4_reg_setup(struct op_counter_config *ctr,
                             struct op_system_config *sys,
                             int num_ctrs)
@@ -59,6 +66,8 @@ static void power4_reg_setup(struct op_counter_config *ctr,
        mmcr1_val = sys->mmcr1;
        mmcra_val = sys->mmcra;
 
+       backtrace_spinlocks = sys->backtrace_spinlocks;
+
        for (i = 0; i < num_counters; ++i)
                reset_value[i] = 0x80000000UL - ctr[i].count;
 
@@ -88,7 +97,7 @@ static void power4_cpu_setup(void *unused)
        mtspr(SPRN_MMCR0, mmcr0);
 
        mmcr0 |= MMCR0_FCM1|MMCR0_PMXE|MMCR0_FCECE;
-       mmcr0 |= MMCR0_PMC1INTCONTROL|MMCR0_PMCNINTCONTROL;
+       mmcr0 |= MMCR0_PMC1CE|MMCR0_PMCjCE;
        mtspr(SPRN_MMCR0, mmcr0);
 
        mtspr(SPRN_MMCR1, mmcr1_val);
@@ -170,19 +179,38 @@ static void __attribute_used__ kernel_unknown_bucket(void)
 {
 }
 
+static unsigned long check_spinlock_pc(struct pt_regs *regs,
+                                      unsigned long profile_pc)
+{
+       unsigned long pc = instruction_pointer(regs);
+
+       /*
+        * If both the SIAR (sampled instruction) and the perfmon exception
+        * occurred in a spinlock region then we account the sample to the
+        * calling function. This isnt 100% correct, we really need soft
+        * IRQ disable so we always get the perfmon exception at the
+        * point at which the SIAR is set.
+        */
+       if (backtrace_spinlocks && in_lock_functions(pc) &&
+                       in_lock_functions(profile_pc))
+               return regs->link;
+       else
+               return profile_pc;
+}
+
 /*
  * On GQ and newer the MMCRA stores the HV and PR bits at the time
  * the SIAR was sampled. We use that to work out if the SIAR was sampled in
  * the hypervisor, our exception vectors or RTAS.
  */
-static unsigned long get_pc(void)
+static unsigned long get_pc(struct pt_regs *regs)
 {
        unsigned long pc = mfspr(SPRN_SIAR);
        unsigned long mmcra;
 
        /* Cant do much about it */
        if (!mmcra_has_sihv)
-               return pc;
+               return check_spinlock_pc(regs, pc);
 
        mmcra = mfspr(SPRN_MMCRA);
 
@@ -196,10 +224,6 @@ static unsigned long get_pc(void)
        if (mmcra & MMCRA_SIPR)
                return pc;
 
-       /* Were we in our exception vectors? */
-       if (pc < 0x4000UL)
-               return (unsigned long)__va(pc);
-
 #ifdef CONFIG_PPC_PSERIES
        /* Were we in RTAS? */
        if (pc >= rtas.base && pc < (rtas.base + rtas.size))
@@ -207,12 +231,16 @@ static unsigned long get_pc(void)
                return *((unsigned long *)rtas_bucket);
 #endif
 
+       /* Were we in our exception vectors or SLB real mode miss handler? */
+       if (pc < 0x1000000UL)
+               return (unsigned long)__va(pc);
+
        /* Not sure where we were */
        if (pc < KERNELBASE)
                /* function descriptor madness */
                return *((unsigned long *)kernel_unknown_bucket);
 
-       return pc;
+       return check_spinlock_pc(regs, pc);
 }
 
 static int get_kernel(unsigned long pc)
@@ -236,10 +264,9 @@ static void power4_handle_interrupt(struct pt_regs *regs,
        int is_kernel;
        int val;
        int i;
-       unsigned int cpu = smp_processor_id();
        unsigned int mmcr0;
 
-       pc = get_pc();
+       pc = get_pc(regs);
        is_kernel = get_kernel(pc);
 
        /* set the PMM bit (see comment below) */
@@ -249,7 +276,7 @@ static void power4_handle_interrupt(struct pt_regs *regs,
                val = ctr_read(i);
                if (val < 0) {
                        if (oprofile_running && ctr[i].enabled) {
-                               oprofile_add_sample(pc, is_kernel, i, cpu);
+                               oprofile_add_pc(pc, is_kernel, i);
                                ctr_write(i, reset_value[i]);
                        } else {
                                ctr_write(i, 0);